Unsupervised Segmentation of Action Segments in Egocentric Videos using Gaze

no code implementations • 30 Sep 2017 • I. Hipiny, H. Ujir, J. L. Minoi, S. F. Samson Juan, M. A. Khairuddin, M. S. Sunar

By tracking two simple motion-based parameters inside successive regions-of-interest, we discover a finite set of temporal cuts.

Activity Recognition Retrieval +1